From 93427dc62d250827fce5b9d4e33eb3ca5f18f226 Mon Sep 17 00:00:00 2001 From: Pritam Dodeja Date: Fri, 6 May 2022 05:08:09 -0400 Subject: [PATCH] Fix to only transform raw data when requested. When read_raw_data_for_training is set to False when invoking the main function, common.transform_data was being called on raw train and test data anyway. This fix moves the transformation to the block where read_raw_data_for_training is True. The scenario here is the data has already been preprocessed, and the user wishes to re-use that preprocessed data. --- examples/census_example_v2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/census_example_v2.py b/examples/census_example_v2.py index 66d37680..4c3ac8a4 100644 --- a/examples/census_example_v2.py +++ b/examples/census_example_v2.py @@ -237,11 +237,11 @@ def main(input_data_dir, train_data_file = os.path.join(input_data_dir, 'adult.data') test_data_file = os.path.join(input_data_dir, 'adult.test') - common.transform_data(train_data_file, test_data_file, working_dir) if read_raw_data_for_training: raw_train_and_eval_patterns = (train_data_file, test_data_file) transformed_train_and_eval_patterns = None + common.transform_data(train_data_file, test_data_file, working_dir) else: train_pattern = os.path.join(working_dir, common.TRANSFORMED_TRAIN_DATA_FILEBASE + '*')